A dynamic load identification method using gru neural network

Zaifei Kang, Te Yang, Shuya Liang, Zhichun Yang

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

The Gated Recurrent Unit (GRU) neural network neural network is introduced into the identification of dynamic load. Using the "memory" characteristics of the GRU neural network combined with the solution principle of vibration response, a time-domain dynamic load identification method based on GRU neural network is proposed. Dynamic load identification experiments are carried out on a stiffened panel subjected to two stationary random point loads. The results show that the time histories of the loads can be accurately identified by using this method. At the same time, the power spectral density functions of the identified loads and the actual loads also have a high degree of coincidence. The proposed method does not need to establish the dynamic model of the structure, which provides an effective load identification approach for engineering structures.

源语言英语
主期刊名"Advances in Acoustics, Noise and Vibration - 2021" Proceedings of the 27th International Congress on Sound and Vibration, ICSV 2021
编辑Eleonora Carletti, Malcolm Crocker, Marek Pawelczyk, Jiri Tuma
出版商Silesian University Press
ISBN(电子版)9788378807995
出版状态已出版 - 2021
活动27th International Congress on Sound and Vibration, ICSV 2021 - Virtual, Online
期限: 11 7月 202116 7月 2021

出版系列

姓名"Advances in Acoustics, Noise and Vibration - 2021" Proceedings of the 27th International Congress on Sound and Vibration, ICSV 2021
ISSN(印刷版)2329-3675

会议

会议27th International Congress on Sound and Vibration, ICSV 2021
Virtual, Online
时期11/07/2116/07/21

指纹

探究 'A dynamic load identification method using gru neural network' 的科研主题。它们共同构成独一无二的指纹。

引用此